Cleaning things up a bit

notebooks/APICarbonQuery.ipynb

@@ -0,0 +1,200 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c82eb8a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json, requests, urllib"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "45a53227",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5ee17bd2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = requests.get(\"https://huggingface.co/api/models?filter=co2_eq_emissions\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "805a29d7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Out of 78 models, 78 of them reported carbon emissions\n"
+     ]
+    }
+   ],
+   "source": [
+    "modelcount=0\n",
+    "carboncount=0\n",
+    "\n",
+    "carbon_df = pd.DataFrame(columns=['name','task','carbon'])\n",
+    "\n",
+    "for model in response.json():\n",
+    "    modelcount+=1\n",
+    "    if model['private'] == False:\n",
+    "        try:\n",
+    "            readme = urllib.request.urlopen(\"https://huggingface.co/\"+model['modelId']+\"/raw/main/README.md\")\n",
+    "            for line in readme:\n",
+    "                decoded_line = line.decode(\"utf-8\")\n",
+    "                if 'co2_eq_emissions' in decoded_line:\n",
+    "                    carboncount+=1\n",
+    "                    #print(model['modelId'], model['pipeline_tag'], decoded_line.split(\":\")[1])\n",
+    "                    try:\n",
+    "                        carbon_df.at[carboncount,'name'] = str(model['modelId'])\n",
+    "                        carbon_df.at[carboncount,'task'] = str(model['pipeline_tag'])\n",
+    "                        carbon_df.at[carboncount,'carbon'] = float(decoded_line.split(\":\")[1].replace('\\n',''))\n",
+    "                    except:\n",
+    "                        carbon_df.at[carboncount,'name'] = str(model['modelId'])\n",
+    "                        carbon_df.at[carboncount,'task'] = ''\n",
+    "                        carbon_df.at[carboncount,'carbon'] = float(decoded_line.split(\":\")[1].replace('\\n',''))\n",
+    "        except:\n",
+    "            continue\n",
+    "print(\"Out of \"+str(modelcount)+\" models, \"+str(carboncount)+ \" of them reported carbon emissions\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ce21fde5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>name</th>\n",
+       "      <th>task</th>\n",
+       "      <th>carbon</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Aimendo/autonlp-triage-35248482</td>\n",
+       "      <td>text-classification</td>\n",
+       "      <td>7.989145</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Anorak/nirvana</td>\n",
+       "      <td>text2text-generation</td>\n",
+       "      <td>4.214013</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>AryanLala/autonlp-Scientific_Title_Generator-3...</td>\n",
+       "      <td>text2text-generation</td>\n",
+       "      <td>137.605741</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Crasher222/kaggle-comp-test</td>\n",
+       "      <td>text-classification</td>\n",
+       "      <td>60.744727</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Emanuel/autonlp-pos-tag-bosque</td>\n",
+       "      <td>token-classification</td>\n",
+       "      <td>6.210727</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                name                  task  \\\n",
+       "1                    Aimendo/autonlp-triage-35248482   text-classification   \n",
+       "2                                     Anorak/nirvana  text2text-generation   \n",
+       "3  AryanLala/autonlp-Scientific_Title_Generator-3...  text2text-generation   \n",
+       "4                        Crasher222/kaggle-comp-test   text-classification   \n",
+       "5                     Emanuel/autonlp-pos-tag-bosque  token-classification   \n",
+       "\n",
+       "       carbon  \n",
+       "1    7.989145  \n",
+       "2    4.214013  \n",
+       "3  137.605741  \n",
+       "4   60.744727  \n",
+       "5    6.210727  "
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "carbon_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "fe01a841",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "carbon_df.to_pickle(\"./carbon_df.pkl\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "datametrics",
+   "language": "python",
+   "name": "datametrics"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}